Github user wzhfy commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18309#discussion_r122499294
  
    --- Diff: 
sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala ---
    @@ -128,6 +129,48 @@ class StatisticsSuite extends 
StatisticsCollectionTestBase with TestHiveSingleto
           TableIdentifier("tempTable"), ignoreIfNotExists = true, purge = 
false)
       }
     
    +  test("SPARK-21079 - analyze table with location different than that of 
individual partitions") {
    +    def queryTotalSize(tableName: String): BigInt =
    +      
spark.table(tableName).queryExecution.analyzed.stats(conf).sizeInBytes
    +
    +    withTempPaths(4) { (paths) => paths match {
    +      case tablePath :: partitionPaths =>
    +        sql(
    +          s"""
    +            |CREATE TABLE analyzeTable_part (key STRING, value STRING) 
PARTITIONED BY (ds STRING)
    +            |LOCATION '${tablePath}'
    +          """.stripMargin).collect()
    +
    +        val partitionDates = List("2010-01-01", "2010-01-02", "2010-01-03")
    +        partitionDates.zip(partitionPaths).foreach(p => {
    +          val ds = p._1
    +          val path = p._2
    +          sql(
    +            s"""
    +              |ALTER TABLE analyzeTable_part ADD PARTITION (ds='${ds}')
    +              |LOCATION '${path.toString}'
    +            """.stripMargin).collect()
    +          sql(
    +            s"""
    +              |INSERT INTO TABLE analyzeTable_part PARTITION (ds='${ds}')
    +              |SELECT * FROM src
    +            """.
    +              stripMargin).collect()
    +          }
    +        )
    +
    +        // Modify table location to not match location of individual 
partitions
    +        sql("ALTER TABLE analyzeTable_part SET LOCATION 
'file:/do/not/use'").collect()
    +
    +        sql("ANALYZE TABLE analyzeTable_part COMPUTE STATISTICS noscan")
    +
    +        assert(queryTotalSize("analyzeTable_part") === BigInt(17436))
    +
    +        sql("DROP TABLE analyzeTable_part").collect()
    --- End diff --
    
    use `withTable` to include the test, then we don't need to drop table 
explicitly.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to